How to Use the Greptile MCP in Mastra AI

Q: How do I track Greptile token consumption across my Mastra AI workflows?

You integrate the getgreptileusage tool into your agent's monitoring loop to keep tabs on API spend. This allows your workflow to pause or send an alert if a running job exceeds its allocated budget.

Q: How do I manage multiple repositories in a single agent session?

Your agent uses listrepositories to find which codebases are already indexed before deciding where to search. If a target repository is missing, the agent can programmatically call indexrepository to queue it up.

Build resilient, self-healing codebase workflows using Greptile with Mastra AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Greptile MCP to Mastra AI

Create your Vinkius account to connect Greptile to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Greptile with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Repository Indexing Workflows

The `index_repository` tool initiates the background indexing process for any public or private repository. Within a Mastra AI workflow, you can trigger this tool automatically whenever a webhook detects a new project creation. This ensures your agents always work with fresh code. If the indexing job fails due to network hiccups, the framework's built-in retry engine handles the backoff automatically. You don't have to write custom loop logic to retry the `reindex_repository` call; Mastra handles the state transitions behind the scenes.

Multi-Step Code Analysis with Mastra AI

The `query_with_context` tool maintains session state across complex multi-step reasoning chains. Your agent can ask a question about an API route, receive the response, and immediately follow up with a request to generate test cases. The session context persists without manual payload management. Developers combine this with `get_file_info` to inspect file sizes and import structures before running heavy model queries. This step keeps your token usage low and prevents your MCP agents from getting lost in massive files.

Guardrails for Automated Code Modifications

The `search_by_filepath` tool isolates specific files to verify their contents before your agents recommend changes. This mechanism prevents your autonomous workflows from hallucinating file structures or writing to non-existent paths. It acts as a safety valve for your automated pipeline. You configure Mastra's human-in-the-loop approval feature to pause execution when the agent wants to execute a write action. The agent gathers the necessary context using this MCP Server, presents the diff, and waits for a developer's green light.

Setup guide

Set up Greptile MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Greptile tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "greptile-mcp-client",
  servers: {
    "greptile-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Greptile Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Greptile tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Greptile transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Greptile. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Greptile now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Greptile MCP in Mastra AI

You initialize the MCP client with the server's HTTP URL and spread the fetched tools into your agent's configuration. The framework automatically maps the schemas so your agent knows exactly when to call query_codebase.

Yes, the framework's workflow engine uses exponential backoff to retry tools like query_codebase if they hit rate limits. You define the retry policy directly in your workflow step definition to handle transient API errors gracefully.

You integrate the get_greptile_usage tool into your agent's monitoring loop to keep tabs on API spend. This allows your workflow to pause or send an alert if a running job exceeds its allocated budget.

Your agent uses list_repositories to find which codebases are already indexed before deciding where to search. If a target repository is missing, the agent can programmatically call index_repository to queue it up.

Your repository metadata and code files are processed through secure, ephemeral V8 isolates that disconnect immediately after the session ends. The underlying MCP infrastructure ensures your proprietary code is never stored in persistent shared caches.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript